Skip to main content

Configuration Reference

This reference is grounded in runtime defaults and env parsing code.

Primary Sources​

  • Local runtime defaults: docker-compose.yml
  • Gateway config file: services/gateway/config/default.toml
  • Query-engine cache env parsing: services/query-engine/src/cache.rs
  • GPU config env parsing: plugins/gpu-accel/src/config.rs
  • ML config env parsing: plugins/ml-engine/src/config.rs

Gateway​

default.toml​

KeyDefault
server.listen_addr0.0.0.0:27017
server.max_connections50000
server.idle_timeout_secs300
coordinator.addrthermocline-coordinator:9090
coordinator.connect_timeout_ms5000
coordinator.request_timeout_ms60000
metrics.enabledtrue
metrics.addr0.0.0.0:9100
metrics.path/metrics
logging.levelinfo
logging.formatjson

Compose Environment (Representative)​

  • GATEWAY_LISTEN_ADDR
  • GATEWAY_ADVERTISED_HOST
  • GATEWAY_COORDINATOR_ADDR
  • GATEWAY_SE_ADDR
  • GATEWAY_MAX_CONNECTIONS
  • GATEWAY_IDLE_TIMEOUT_SECS

Storage Engine (Compose Variables)​

  • SE_DATA_DIR
  • SE_GRPC_ADDR
  • SE_METRICS_PORT
  • SE_WAL_SYNC_MODE
  • SE_MEMTABLE_SIZE
  • SE_MAX_IMMUTABLE_MEMTABLES
  • SE_BLOCK_CACHE_SIZE
  • SE_COMPACTION_THREADS
  • SE_LOG_LEVEL

Coordinator (Compose Variables)​

  • COORDINATOR_GRPC_ADDR
  • COORDINATOR_ETCD_ENDPOINTS
  • COORDINATOR_QE_ADDRS
  • COORDINATOR_SE_ADDRS
  • COORDINATOR_METRICS_ADDR
  • COORDINATOR_SE_WRITE_TIMEOUT_SECS
  • COORDINATOR_SE_READ_TIMEOUT_SECS

Query Engine (Compose Variables)​

  • GRPC_LISTEN_ADDR
  • STORAGE_PROVIDER
  • STORAGE_BUCKET
  • STORAGE_ENDPOINT
  • STORAGE_REGION
  • STORAGE_ALLOW_HTTP
  • AWS_ACCESS_KEY_ID
  • AWS_SECRET_ACCESS_KEY

Intelligent Cache Variables​

  • CACHE_ENABLED
  • CACHE_L1_MAX_CAPACITY
  • CACHE_L2_ENABLED
  • CACHE_L2_PATH
  • CACHE_L2_MAX_SIZE_BYTES
  • CACHE_L3_ENABLED
  • CACHE_L3_SERVER_ENABLED
  • CACHE_L3_BIND_ADDRESS
  • CACHE_L3_ADDRESSES
  • CACHE_QUERY_RESULT_TTL_SECS

GPU Variables​

  • GPU_ACCEL_ENABLED
  • GPU_ACCEL_DEVICE_ID
  • GPU_ACCEL_BATCH_THRESHOLD
  • GPU_ACCEL_MAX_MEMORY_MB
  • GPU_ACCEL_VECTOR_CACHE_MB
  • GPU_ACCEL_BLOCK_SIZE
  • GPU_ACCEL_PRIORITY_SCHEDULING
  • GPU_ACCEL_MULTI_QUERY_BATCHING
  • GPU_ACCEL_GPU_RERANKING

ML Variables​

  • ML_ENGINE_ENABLED
  • ML_ENGINE_MAX_ITERATIONS
  • ML_ENGINE_CONVERGENCE_TOLERANCE
  • ML_ENGINE_MAX_FEATURES
  • ML_ENGINE_MAX_SAMPLES
  • ML_ENGINE_MAX_CLUSTERS
  • ML_ENGINE_MAX_TREE_DEPTH
  • ML_ENGINE_MINI_BATCH_SIZE
  • ML_ENGINE_KMEANS_N_INIT
  • ML_ENGINE_REGULARIZATION_ALPHA
  • ML_ENGINE_BATCH_PREDICTION
  • ML_ENGINE_CUSTOM_ITERATIONS
  • ML_ENGINE_MODEL_STORE_DIR